Take a screenshot (returns image)
AI agents call ira_screenshot to retrieve information from IRA-RESEARCHER without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
A screenshot operation captures and returns data from the rendered browser display. It has no side effects on the underlying system or data—it does not create, modify, delete, execute code, or commit financial transactions. This is a pure Read operation with minimal risk even if misused, as the worst outcome would be unauthorized visibility of what is already displayed on screen.
From the tool's definition Tool name 'ira_screenshot' and description 'Take a screenshot (returns image)' indicate it retrieves visual data from the current browser state without modifying anything.
Attacks that exploit this kind of access
Take a screenshot (returns image). It is categorised as a Read tool in the IRA-RESEARCHER MCP Server, which means it retrieves data without modifying state.
Register the IRA-RESEARCHER MCP server in PolicyLayer and add a rule for ira_screenshot: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches IRA-RESEARCHER. Nothing to install.
ira_screenshot is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the ira_screenshot rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for ira_screenshot. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
ira_screenshot is provided by the IRA-RESEARCHER MCP server (neuralnexustech/ira-researcher). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →